Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    in a script, lines beginning with a variable enclosed in brackets

    oai_token-act-pair · gemini-2.0-flash

    Code and "-ated" suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.46
    glected
    -0.45
    ensibility
    -0.45
     oft
    -0.44
    anyaan
    -0.44
     populaire
    -0.44
    ensible
    -0.43
    ast
    -0.43
    ziplin
    -0.43
     An
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.92
     located
    0.83
    Located
    0.79
    dafx
    0.76
    located
    0.76
     Located
    0.75
    twimg
    0.74
     расположен
    0.73
     BoxDecoration
    0.71
     locating
    0.70
    Act Density 0.695%

    No Known Activations